uncbiag / easyreg Goto Github PK
View Code? Open in Web Editor NEWan image registration/augmentation/segmentation package
License: Other
an image registration/augmentation/segmentation package
License: Other
https://github.com/uncbiag/mermaid can not be accessible without being a member of uncbiag. If mermaid is also going to be public, please ignore that.
It might be good to deploy a website to www.cs.unc.edu/{labname}/easyreg or anywhere that's possible. (The sphinx output)
Also, doc/ directory shouldn't be included in the final version, it just increases the download size.
The activation of easyreg is using the command conda, not source like a virtual enviroment.
The mistake is in the installation part.
I/O examples can be moved under demos folder.
(https://github.com/uncbiag/easyreg/tree/master/data_pre/examples)
The optional download demo operation requires gdown
, yet the requirements are installed after that operation. Thus, the order of installation should be changed.
Files like .config, .idea, .vscode shouldn't be included in the repository. They should be on .gitignore
In the train_reg.py the name of the setting file for lpba is "cur_task_setting.json", however, in the folder it is "curr_task_setting.json". This is causing unexpected errors.
Paths like
https://github.com/uncbiag/easyreg/blob/master/settings/data_settings.json#L17
Shouldn't be set as a setting. User should be able to define such path via command line arguments or it should be indicated in the README.md file.
Zenodo enables creation of an open source scientific software citation, complete with a DOI. This enable recognition of the work and reproducibility through identification of computational dependencies.
An GitHub README badge with the citation that is automatically updated when a GitHub Release is created can be generated as documented here:
Many people are sharing BibTeX entries of the related papers to repository, so it might be worthful to follow that practice.
I am looking for Cross model image registration for some of my projects and I am wondering will it support cross-modal images.
I have attempted to run a demo for demons registration. How can I extract the resulting images of registration?
Thanks in advance.
I try to run ./demo/demo_for_easyreg_eval.py via python ./demo_for_easyreg_eval.py --setting_folder_path ./demo_settings/mermaid/opt_vsvf --gpu_id 0 --task_output_path ./demo_output/mermaid/
opt_vsvf -s ./image/image_1_save.nii.gz -t ./image/image_2_save.nii.gz.
However, the error had been occurred :
Traceback (most recent call last):
File "./demo_for_easyreg_eval.py", line 247, in
do_registration_eval(args, registration_pair_list, pair_name_list)
File "./demo_for_easyreg_eval.py", line 162, in do_registration_eval
run_one_task(tsm_json_path, dm_json_path)
File "D:\Python_Code\easyreg\easyreg\piplines.py", line 58, in run_one_task
pipline.initialize(task_setting_pth,data_setting_pth,data_loaders)
File "D:\Python_Code\easyreg\easyreg\piplines.py", line 28, in initialize
self.model = create_model(self.tsk_opt)
File "D:\Python_Code\easyreg\easyreg\create_model.py", line 29, in create_model
from .mermaid_iter import MermaidIter
File "D:\Python_Code\easyreg\easyreg\mermaid_iter.py", line 1, in
from .base_mermaid import MermaidBase
File "D:\Python_Code\easyreg\easyreg\base_mermaid.py", line 2, in
from .base_reg_model import RegModelBase
File "D:\Python_Code\easyreg\easyreg\base_reg_model.py", line 2, in
from .utils import *
File "D:\Python_Code\easyreg\easyreg\utils.py", line 7, in
import mermaid.image_sampling as py_is
ModuleNotFoundError: No module named 'mermaid'
Ana I can't found this file in this project.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.